You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: articles/ai-services/language-service/conversational-language-understanding/glossary.md
+3-3Lines changed: 3 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -38,7 +38,7 @@ A model is an object that's trained to do a certain task, in this case conversat
38
38
39
39
## Overfitting
40
40
41
-
Overfitting happens when the model is fixated on the specific examples and is not able to generalize well.
41
+
Overfitting happens when the model is fixated on the specific examples and isn't able to generalize well.
42
42
43
43
## Precision
44
44
Measures how precise/accurate your model is. It's the ratio between the correctly identified positives (true positives) and all identified positives. The precision metric reveals how many of the predicted classes are correctly labeled.
@@ -53,14 +53,14 @@ Measures the model's ability to predict actual positive classes. It's the ratio
53
53
A regular expression entity represents a regular expression. Regular expression entities are exact matches.
54
54
55
55
## Schema
56
-
Schema is defined as the combination of intents and entities within your project. Schema design is a crucial part of your project's success. When creating a schema, you want think about which intents and entities should be included in your project
56
+
Schema is defined as the combination of intents and entities within your project. Schema design is a crucial part of your project's success. When creating a schema, you want to think about which intents and entities should be included in your project.
57
57
58
58
## Training data
59
59
Training data is the set of information that is needed to train a model.
60
60
61
61
## Utterance
62
62
63
-
An utterance is user input that is short text representative of a sentence in a conversation. It is a natural language phrase such as "book 2 tickets to Seattle next Tuesday". Example utterances are added to train the model and the model predicts on new utterance at runtime
63
+
An utterance is user input that is short text representative of a sentence in a conversation. It's a natural language phrase such as "book 2 tickets to Seattle next Tuesday". Example utterances are added to train the model and the model predicts on new utterance at runtime
Copy file name to clipboardExpand all lines: articles/ai-services/language-service/question-answering/how-to/migrate-qnamaker-to-question-answering.md
+8-8Lines changed: 8 additions & 8 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -9,7 +9,7 @@ ms.topic: how-to
9
9
ms.date: 12/19/2023
10
10
ms.custom: language-service-question-answering
11
11
---
12
-
# Migrate from QnA Maker to custom question qnswering
12
+
# Migrate from QnA Maker to custom question answering
13
13
14
14
**Purpose of this document:** This article aims to provide information that can be used to successfully migrate applications that use QnA Maker to custom question answering. Using this article, we hope customers will gain clarity on the following:
@@ -65,7 +65,7 @@ When you are looking at migrating to custom question answering, please consider
65
65
66
66
- Users may select a higher tier with higher capacity, which will impact overall price they pay. It doesn’t impact the price on language component of custom question answering.
67
67
68
-
- “Text Records” in custom question answering features refers to the query submitted by the user to the runtime, and it is a concept common to all features within Language service. Sometimes a query may have more text records when the query length is higher.
68
+
- “Text Records” in custom question answering features refers to the query submitted by the user to the runtime, and it's a concept common to all features within Language service. Sometimes a query may have more text records when the query length is higher.
69
69
70
70
**Example price estimations**
71
71
@@ -76,7 +76,7 @@ When you are looking at migrating to custom question answering, please consider
Summary: Customers should save cost across the most common configurations as seen in the relative cost column.
79
+
Summary: Customers should save cost across the most common configurations as seen in the relative cost column.
80
80
81
81
Here you can find the pricing details for [custom question answering](https://azure.microsoft.com/pricing/details/cognitive-services/language-service/) and [QnA Maker](https://azure.microsoft.com/pricing/details/cognitive-services/qna-maker/).
82
82
@@ -101,7 +101,7 @@ Following are the broad migration phases to consider:
101
101
102
102

103
103
104
-
Additional links which can help you are given below:
104
+
Additional links which can help you're given below:
@@ -115,7 +115,7 @@ This topic compares two hypothetical scenarios when migrating from QnA Maker to
115
115
> An attempt has been made to ensure these scenarios are representative of real customer migrations, however, individual customer scenarios will of course differ. Also, this article doesn't include pricing details. Visit the [pricing](https://azure.microsoft.com/pricing/details/cognitive-services/language-service/) page for more information.
116
116
117
117
> [!IMPORTANT]
118
-
> Each custom question answering project is equivalent to a knowledge base in QnA Maker. Resource level settings such as Role-based access control (RBAC) are not migrated to the new resource. These resource level settings would have to be reconfigured for the language resource post migration. You will also need to [re-enable analytics](analytics.md) for the language resource.
118
+
> Each custom question answering project is equivalent to a knowledge base in QnA Maker. Resource level settings such as Role-based access control (RBAC) are not migrated to the new resource. These resource level settings would have to be reconfigured for the language resource post migration. You'll also need to [re-enable analytics](analytics.md) for the language resource.
119
119
120
120
### Migration scenario 1: No custom authoring portal
Copy file name to clipboardExpand all lines: articles/ai-services/language-service/question-answering/how-to/migrate-qnamaker.md
+11-11Lines changed: 11 additions & 11 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -9,7 +9,7 @@ ms.date: 12/19/2023
9
9
ms.custom: language-service-question-answering
10
10
---
11
11
12
-
# Migrate from QnA Maker to custom question answering
12
+
# Migrate from QnA Maker knowledge bases to custom question answering
13
13
14
14
> [!NOTE]
15
15
> You can also migrate to [Azure OpenAI](../../../qnamaker/How-To/migrate-to-openai.md).
@@ -32,7 +32,7 @@ This [SDK Migration Guide](https://github.com/Azure/azure-sdk-for-net/blob/Azure
32
32
33
33
You can follow the steps below to migrate knowledge bases:
34
34
35
-
1. Create a [language resource](https://aka.ms/create-language-resource) with custom question answering enabled in advance. When you create the language resource in the Azure portal, you will see the option to enable custom question answering. When you select that option and proceed, you will be asked for Azure Search details to save the knowledge bases.
35
+
1. Create a [language resource](https://aka.ms/create-language-resource) with custom question answering enabled in advance. When you create the language resource in the Azure portal, you'll see the option to enable custom question answering. When you select that option and proceed, you'll be asked for Azure Search details to save the knowledge bases.
36
36
37
37
2. If you want to add knowledge bases in multiple languages to your language resource, visit [Language Studio](https://language.azure.com/) to create your first custom question answering project and select the first option as shown below. Language settings for the language resource can be specified only when creating a project. If you want to migrate existing knowledge bases in a single language to the language resource, you can skip this step.
38
38
@@ -53,12 +53,12 @@ You can follow the steps below to migrate knowledge bases:
53
53
> [!div class="mx-imgBorder"]
54
54
> 
55
55
56
-
6. Select the language resource to which you want to migrate the knowledge bases. You will only be able to see those language resources that have custom question answering enabled. The language setting for the language resource is displayed in the options. You won’t be able to migrate knowledge bases in multiple languages from QnA Maker resources to a language resource if its language setting is not specified.
56
+
6. Select the language resource to which you want to migrate the knowledge bases. You'll only be able to see those language resources that have custom question answering enabled. The language setting for the language resource is displayed in the options. You won’t be able to migrate knowledge bases in multiple languages from QnA Maker resources to a language resource if its language setting isn't specified.
57
57
58
58
> [!div class="mx-imgBorder"]
59
59
> 
60
60
61
-
If you want to migrate knowledge bases in multiple languages to the language resource, you must enable the multiple language setting when creating the first custom question answering project for the language resource. You can do so by following the instructions in step #2. **If the language setting for the language resource is not specified, it is assigned the language of the selected QnA Maker resource**.
61
+
If you want to migrate knowledge bases in multiple languages to the language resource, you must enable the multiple language setting when creating the first custom question answering project for the language resource. You can do so by following the instructions in step #2. **If the language setting for the language resource isn't specified, it is assigned the language of the selected QnA Maker resource**.
62
62
63
63
7. Select all the knowledge bases that you wish to migrate > select **Next**.
64
64
@@ -71,26 +71,26 @@ You can follow the steps below to migrate knowledge bases:
71
71
> If you migrate a knowledge base with the same name as a project that already exists in the target language resource, **the content of the project will be overridden** by the content of the selected knowledge base.
72
72
73
73
> [!div class="mx-imgBorder"]
74
-
> 
74
+
> 
75
75
76
76
9. After resolving the validation errors, select **Start migration**
77
77
78
78
> [!div class="mx-imgBorder"]
79
-
> 
79
+
> 
80
80
81
-
10. It will take a few minutes for the migration to occur. Do not cancel the migration while it is in progress. You can navigate to the migrated projects within the [Language Studio](https://language.azure.com/) post migration.
81
+
10. It will take a few minutes for the migration to occur. Don't cancel the migration while it is in progress. You can navigate to the migrated projects within the [Language Studio](https://language.azure.com/) post migration.
82
82
83
83
> [!div class="mx-imgBorder"]
84
-
> 
84
+
> 
85
85
86
86
If any knowledge bases fail to migrate to custom question answering projects, an error will be displayed. The most common migration errors occur when:
87
87
88
88
- Your source and target resources are invalid.
89
-
- You are trying to migrate an empty knowledge base (KB).
90
-
- You have reached the limit for an Azure Search instance linked to your target resources.
89
+
- You're trying to migrate an empty knowledge base (KB).
90
+
- You've reached the limit for an Azure Search instance linked to your target resources.
91
91
92
92
> [!div class="mx-imgBorder"]
93
-
> 
93
+
> 
94
94
95
95
Once you resolve these errors, you can rerun the migration.
0 commit comments